Data-driven simulation method of multiphase choke performance

Abstract

A data base is updated that contains oil production rate test data. The oil production rate test data are collected, uploaded, and divided into subsets by a downstream-to-upstream pressure ratio. For each subset, the data is split by an oil flow rate. For each resulted subset, the data is split randomly into training data sets and testing data sets. A feed-forward back propagation neural network is built for each subset in the third step. The simulation model is calibrated utilizing actual production history from the training data set. The model performance is tested utilizing actual production history from the testing data set. If the error is within an acceptable and practicable tolerance, the resulting model is used to simulate future multiphase choke performance. Steps are repeated within a specific frequency depending on the production data flow into the data base.

What is claimed is: 
     
         1 . A computer-implemented method, comprising:
 updating a data base that contains oil production rate test data;   collecting and uploading the oil production rate test data, and dividing the oil production rate test data into subsets by a downstream-to-upstream pressure ratio;   for each subset, splitting the data into subset-splits by an oil flow rate;   for each subset-split, splitting the data randomly into training data sets and testing data sets;   building a feed-forward back propagation neural network;   calibrating the simulation model utilizing actual production history from the training data set;   testing the model performance utilizing actual production history from the testing data set;   if the error is within an acceptable and practicable tolerance, proceeding with the resulting model to simulate future choke performance; and   repeating the steps within a specific frequency depending on the production data flow into the data base.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the subsets include a subset for critical flow data with a pressure ratio less than 0.5 and a subset for subcritical flow data with a pressure ratio greater than or equal to 0.5. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the subset-splits include subset-splits for each of a low range below 1200 bbl (barrels) per day, a medium range between 1200 and 2000 bbl/day, and a high range above 2000 bbl/day. 
     
     
         4 . The computer-implemented method of  claim 1 , wherein a split into training data sets and testing data sets follows a breakdown of 80% training and 20% testing. 
     
     
         5 . The method of  claim 1 , wherein feed-forward back propagation neural network includes two hidden layers. 
     
     
         6 . The computer-implemented method of  claim 1 , wherein the feed-forward back propagation neural network is an artificial neural network (ANN) model. 
     
     
         7 . The computer-implemented method of  claim 6 , wherein the ANN model includes a transformation of input variables governed by:
     A=Σ   i=1   4   w   i1   X   i   +b   A  and       B=Σ   i=1   4   w   i2   X   i   +b   B ,   wherein:
 A and B are hidden layer variables, 
 w ij  is a weight from an ith input variable to a jth hidden layer variable A or B, 
 b A  is a bias of A, and 
 b B  is a bias of B, 
   wherein an output variable Y of the model is given by:
     Y=w   A   A+w   B   B+b   Y , 
   and wherein:
 w A  is a weight from A to Y, 
 w B  is a weight from B to Y, and 
 b Y  is a bias of Y. 
   
     
     
         8 . A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
 updating a data base that contains oil production rate test data;   collecting and uploading the oil production rate test data, and dividing the oil production rate test data into subsets by a downstream-to-upstream pressure ratio;   for each subset, splitting the data into subset-splits by an oil flow rate;   for each subset-split, splitting the data randomly into training data sets and testing data sets;   building a feed-forward back propagation neural network;   calibrating the simulation model utilizing actual production history from the training data set;   testing the model performance utilizing actual production history from the testing data set;   if the error is within an acceptable and practicable tolerance, proceeding with the resulting model to simulate future choke performance; and   repeating the steps within a specific frequency depending on the production data flow into the data base.   
     
     
         9 . The non-transitory, computer-readable medium of  claim 8 , wherein the subsets include a subset for critical flow data with a pressure ratio less than 0.5 and a subset for subcritical flow data with a pressure ratio greater than or equal to 0.5. 
     
     
         10 . The non-transitory, computer-readable medium of  claim 8 , wherein the subset-splits include subset-splits for each of a low range below 1200 bbl (barrels) per day, a medium range between 1200 and 2000 bbl/day, and a high range above 2000 bbl/day. 
     
     
         11 . The non-transitory, computer-readable medium of  claim 8 , wherein a split into training data sets and testing data sets follows a breakdown of 80% training and 20% testing. 
     
     
         12 . The non-transitory, computer-readable medium of  claim 8 , wherein feed-forward back propagation neural network includes two hidden layers. 
     
     
         13 . The non-transitory, computer-readable medium of  claim 8 , wherein the feed-forward back propagation neural network is an artificial neural network (ANN) model. 
     
     
         14 . The non-transitory, computer-readable medium of  claim 13 , wherein the ANN model includes a transformation of input variables governed by:
     A=Σ   i=1   4   w   i1   X   i   +b   A  and       B=Σ   i=1   4   w   i2   X   i   +b   B ,   wherein:
 A and B are hidden layer variables, 
 w ij  is a weight from an ith input variable to a jth hidden layer variable A or B, 
 b A  is a bias of A, and 
 b B  is a bias of B, 
   wherein an output variable Y of the model is given by:
     Y=w   A   A+w   B   B+b   Y , 
   and wherein:
 w A  is a weight from A to Y, 
 w B  is a weight from B to Y, and 
 b Y  is a bias of Y. 
   
     
     
         15 . A computer system, comprising:
 a computer memory; and   a hardware processor interoperably coupled with the computer memory and configured to perform operations comprising:
 updating a data base that contains oil production rate test data; 
 collecting and uploading the oil production rate test data, and dividing the oil production rate test data into subsets by a downstream-to-upstream pressure ratio; 
 for each subset, splitting the data into subset-splits by an oil flow rate; 
 for each subset-split, splitting the data randomly into training data sets and testing data sets; 
 building a feed-forward back propagation neural network; 
 calibrating the simulation model utilizing actual production history from the training data set; 
 testing the model performance utilizing actual production history from the testing data set; 
 if the error is within an acceptable and practicable tolerance, proceeding with the resulting model to simulate future choke performance; and 
 repeating the steps within a specific frequency depending on the production data flow into the data base. 
   
     
     
         16 . The computer system of  claim 15 , wherein the subsets include a subset for critical flow data with a pressure ratio less than 0.5 and a subset for subcritical flow data with a pressure ratio greater than or equal to 0.5. 
     
     
         17 . The computer system of  claim 15 , wherein the subset-splits include subset-splits for each of a low range below 1200 bbl (barrels) per day, a medium range between 1200 and 2000 bbl/day, and a high range above 2000 bbl/day. 
     
     
         18 . The computer system of  claim 15 , wherein a split into training data sets and testing data sets follows a breakdown of 80% training and 20% testing. 
     
     
         19 . The computer system of  claim 15 , wherein the feed-forward back propagation neural network is an artificial neural network (ANN) model. 
     
     
         20 . The computer system of  claim 20 , wherein the ANN model includes a transformation of input variables governed by:
     A=Σ   i=1   4   w   i1   X   i   +b   A  and       B=Σ   i=1   4   w   i2   X   i   +b   B ,   wherein:
 A and B are hidden layer variables, 
 w ij  is a weight from an ith input variable to a jth hidden layer variable A or B, 
 b A  is a bias of A, and 
 b B  is a bias of B, 
   wherein an output variable Y of the model is given by:
     Y=w   A   A+w   B   B+b   Y , 
   and wherein:
 w A  is a weight from A to Y, 
 w B  is a weight from B to Y, and 
 b Y  is a bias of Y.